There are various algorithms for reinforcment learning (RL). One way to group them is by "off-policy" and "on-policy". I've heard that SARSA is on-policy, while Q-Learning is off-policy.

I think they work as follows:

enter image description here

enter image description here

My questions are:

  • How exactly is "on-policy RL" and "off-policy RL" defined?
  • What are the advantages / disadvantages of both?
  • $\begingroup$ Please also let me know if there is an error in my pseudocode $\endgroup$ Commented Jul 27, 2016 at 14:35
  • $\begingroup$ I think a good place to start to understand this would be this recent paper : jmlr.org/proceedings/papers/v32/silver14.pdf $\endgroup$
    – Srinivas K
    Commented Aug 2, 2016 at 6:47

1 Answer 1


This was answered in cross-validated and stackoverflow:

The reason that Q-learning is off-policy is that it updates its Q-values using the Q-value of the next state $s′$ and the greedy action $a′$. In other words, it estimates the return (total discounted future reward) for state-action pairs assuming a greedy policy were followed despite the fact that it's not following a greedy policy.

The reason that SARSA is on-policy is that it updates its Q-values using the Q-value of the next state $s′$ and the current policy's action $a′′$. It estimates the return for state-action pairs assuming the current policy continues to be followed.

These slides offer some insight on pros and cons of each one:

  • On-policy methods:

    • attempt to evaluate or improve the policy that is used to make decisions,
    • often use soft action choice, i.e. $\pi(s,a) >0, \forall a$,
    • commit to always exploring and try to find the best policy that still explores,
    • may become trapped in local minima.
  • Off-policy methods:

    • evaluate one policy while following another, e.g. tries to evaluate the greedy policy while following a more exploratory scheme,
    • the policy used for behaviour should be soft,
    • policies may not be sufficiently similar,
    • may be slower (only the part after the last exploration is reliable), but remains more flexible if alternative routes appear.

For reference, these are the formulations of Q-learning and SARSA from Sutton and Barto seminal book:

Q-learning algorithm

SARSA algorithm

P.S.: I referenced and quoted the original answer from a different stackexchange site, as indicated in this meta question.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.